Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
AReaL
Agents & frameworksThe RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
git clone https://github.com/areal-project/AReaL.git -
rl_rvo_nav
Agents & frameworks[RA-Letter 2022] Reinforcement Learned Distributed Multi-Robot Navigation with Reciprocal Velocity Obstacle Shaped Rewards
git clone https://github.com/hanruihua/rl_rvo_nav.git -
Libra
Agents & frameworksLibra: Efficient Resource Management for Agentic RL Post-Training
git clone https://github.com/NetX-lab/Libra.git -
llm-rl-environments-lil-course
Agents & frameworks🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
git clone https://github.com/anakin87/llm-rl-environments-lil-course.git -
Open-AgentRL
Agents & frameworksRLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
git clone https://github.com/Gen-Verse/Open-AgentRL.git -
AWorld
Agents & frameworksSearch, understand, reproduce, and improve an idea with ease
git clone https://github.com/inclusionAI/AWorld.git -
tensorlake
Agents & frameworksTensorlake is a serverless runtime for sandboxes and deploying background agentic applications
git clone https://github.com/tensorlakeai/tensorlake.git -
Relax
Agents & frameworksAn Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
git clone https://github.com/redai-studio/Relax.git -
tokin
Agents & frameworksMake any agent harness token-native.
git clone https://github.com/open-rollout/tokin.git -
AgileRL
Agents & frameworksThe complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
git clone https://github.com/AgileRL/AgileRL.git -
HarborRL
Agents & frameworksAn end-to-end framework for Agentic Reinforcement Learning.
git clone https://github.com/datamllab/HarborRL.git -
maro
Agents & frameworksMulti-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
git clone https://github.com/microsoft/maro.git -
GPTSwarm
Agents & frameworks🐝 The First Self-Improving agents with RL / Prompting Optimization
git clone https://github.com/metauto-ai/GPTSwarm.git -
pytorch-DRL
Agents & frameworksPyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.
git clone https://github.com/ChenglongChen/pytorch-DRL.git -
BenchMARL
Agents & frameworksBenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
git clone https://github.com/facebookresearch/BenchMARL.git -
Awesome-Graphs-Meet-Agents
Agents & frameworks[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents & Agentic Graph Engineering).
git clone https://github.com/YuanchenBei/Awesome-Graphs-Meet-Agents.git -
verl-agent
Agents & frameworksverl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
git clone https://github.com/langfengQ/verl-agent.git -
skrl
Agents & frameworksModular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
git clone https://github.com/Toni-SM/skrl.git -
CaPtain
Agents & frameworksCaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters
git clone https://github.com/waltstephen/CaPtain.git -
axion1_0
Agents & frameworksFrontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released.
git clone https://github.com/bytedance/axion1_0.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.